Abstract: Methods and systems for managing distribution of data are disclosed. The data may be distributed by edge systems to processing systems. The data may be distributed using a data pipeline. The data pipeline may include functionality to process data using different modalities depending on the type of data and operable connectivity between the edge systems and processing systems. By modifying the manner in which the data is processed, limitations in operable connectivity may be managed and a broader array of different types of data may be more efficiently distributed.

Abstract: An edge compute network includes an endpoint device and an information handling system. The endpoint device includes a network interface configured to operate with no open inbound network ports and to provide an outbound request on a predetermined network port. The information handling system includes first and second reverse proxies and instantiates an endpoint orchestrator. The first reverse proxy receives the outbound request and provides the outbound request to the second reverse proxy. The second reverse proxy provides the outbound request to the endpoint orchestrator which authenticates the endpoint device based upon the outbound request and provides authentication information to the endpoint device. The endpoint device authenticates the information handling system based upon the authentication information, and opens the predetermined network port to the information handling system in response to authenticating the information handling system.

Abstract: A computer-implemented method identifies one or more concepts from a document, wherein the document comprises information on completing a task. The method computes a relevance value of an utterance with respect to completing the task using the one or more identified concepts. The method removes the utterance from a dialog model to be used for completing the task when the relevance value of the utterance is below a given threshold value.

Abstract: A computer-implemented method identifies one or more concepts from a document, wherein the document comprises information on completing a task. The method computes a relevance value of an utterance with respect to completing the task using the one or more identified concepts. The method removes the utterance from a dialog model to be used for completing the task when the relevance value of the utterance is below a given threshold value.